Can we stop this kind of misinformation? Training a model to map a token to individual letters are no harder than training a model to be fluent at English. Arithmetics with small number of digits are achievable as well. You can just try a small 7B model yourself. If you don't know where to start, try the mistral instruct v0.2, and this is how it goes,
> [INST] Spell out the following word letter by letter: margorczynski [/INST] m - a - r - g - o - r - c - z - y - n - s - k - i
> So, the word "margorczynski" spelled out letter by letter is: m-a-r-g-o-r-c-z-y-n-s-k-i.
The text between `[INST]` and `[/INST]` is the input. The text after `[/INST]` is the output.